The present disclosure provides a speech interactive method and device. The method includes: during a process of displaying an interface of an application, detecting a first user operation; in response to the first user operation, querying a speech instruction associated with the application based on the application containing the interface and querying a system general speech instruction; setting the speech instruction and the system general speech instruction as applicable speech instructions for the application; and providing a prompt based on the applicable speech instructions to perform a speech interaction.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A speech interactive method, comprising: during a process of displaying an interface of an application, detecting a first user operation, wherein the first user operation is an operation for triggering a speech input widget; in response to the first user operation, querying a speech instruction associated with the application based on the application containing the interface, and querying a system general speech instruction; setting the speech instruction associated with the application and the system general speech instruction as applicable speech instructions for the application; providing a prompt based on the applicable speech instructions; wherein providing the prompt based on the applicable speech instructions comprises: querying a non-speech operation detected before detecting the first user operation; determining a target speech instruction from the applicable speech instructions based on the non-speech operation, wherein the non-speech operation can be replaced with the target speech instruction; and displaying the applicable speech instructions and highlighting the target speech instruction to prompt the user to use the target speech instruction to replace the non-speech operation.
This invention relates to speech interaction within software applications and addresses the problem of efficiently guiding users to utilize relevant voice commands. The method involves displaying an application interface and detecting a user action that activates a speech input widget. Upon activation, the system retrieves speech instructions specifically associated with the current application and also general system-wide speech instructions. These retrieved instructions are then designated as the applicable speech instructions for that application. A prompt is then presented to the user, informed by these applicable speech instructions. This prompt generation involves examining any non-speech user operation that occurred immediately before the speech input widget was activated. Based on this prior non-speech operation, a specific "target speech instruction" is identified from the applicable speech instructions. This target speech instruction is one that can effectively replace the detected non-speech operation. The system then displays all applicable speech instructions, but highlights the identified target speech instruction, thereby encouraging the user to employ this specific voice command as an alternative to their previous manual action.
2. The method of claim 1 , wherein, after setting the speech instruction associated with the application and the system general speech instruction as the applicable speech instructions for the application, the method further comprises: when detecting a second user operation for inputting a speech, in response to the second user operation, selecting a recommended speech instruction from the applicable speech instructions; and providing the prompt based on the recommended speech instruction.
This invention relates to speech input systems for applications, particularly improving user interaction by dynamically selecting and prompting speech instructions. The problem addressed is the inefficiency of generic speech input systems that do not adapt to specific application contexts, leading to user confusion or incorrect inputs. The method involves setting speech instructions for an application, including both application-specific and system-wide general speech instructions. When a user initiates a speech input, the system detects the operation and selects a recommended speech instruction from the predefined applicable instructions. The system then provides a prompt based on this recommended instruction, guiding the user to input the most relevant speech command for the current context. This ensures that the speech input aligns with the application's functionality, reducing errors and improving user experience. The method dynamically adapts the speech input process by filtering and recommending contextually appropriate instructions, enhancing usability in applications where speech commands vary based on the task or interface state. The system avoids overwhelming the user with irrelevant options by prioritizing instructions that are most likely to be useful in the current scenario. This approach is particularly valuable in applications with complex or frequently changing speech command sets, such as virtual assistants, productivity tools, or multimedia applications.
3. The method of claim 2 , wherein, selecting the recommended speech instruction from the applicable speech instructions comprises: querying a usage counter of each applicable speech instruction; and selecting the recommended speech instruction from the applicable speech instructions based on the usage counter.
This invention relates to speech instruction selection in a voice-controlled system, addressing the challenge of efficiently recommending the most relevant speech commands to users. The system identifies applicable speech instructions based on user context, such as location or device state, and further refines selection by analyzing usage frequency. Each applicable speech instruction is associated with a usage counter that tracks how often it has been executed. The system queries these counters and selects the recommended speech instruction based on the highest usage count, prioritizing frequently used commands to improve user experience and efficiency. This approach ensures that the most relevant and commonly used instructions are presented to the user, reducing decision fatigue and enhancing interaction speed. The method may also involve filtering or ranking instructions based on additional criteria, such as recency or user preferences, to further optimize recommendations. The invention is particularly useful in smart home systems, virtual assistants, or other voice-controlled environments where quick and accurate command selection is critical.
4. The method of claim 2 , wherein, selecting the recommended speech instruction from the applicable speech instructions comprises: querying a software update version for each newly added applicable speech instruction; and selecting a latest applicable speech instruction from the applicable speech instructions as the recommended speech instruction based on the software update version.
This invention relates to speech instruction selection in software systems, particularly for recommending the most up-to-date speech instructions to users. The problem addressed is ensuring users receive the latest and most relevant speech instructions, especially when multiple applicable instructions exist. The solution involves a method for selecting a recommended speech instruction from a set of applicable instructions by evaluating their associated software update versions. The method first queries the software update version for each newly added applicable speech instruction. Then, it selects the latest applicable speech instruction based on these versions, ensuring users receive the most current instruction. This approach helps maintain consistency and relevance in speech-based interactions by prioritizing the most recently updated instructions. The method is part of a broader system that identifies applicable speech instructions based on user context and system capabilities, ensuring the selected instruction is both relevant and up-to-date. By leveraging version information, the system avoids outdated or redundant instructions, improving user experience and system efficiency.
5. The method of claim 4 , wherein, before selecting the latest applicable speech instruction from the applicable speech instructions as the recommended speech instruction based on the software update version, the method further comprises: determining the latest applicable speech instruction based on a version number of the software update version; and providing the prompt when a number of occurrences of providing the prompt to select the latest applicable speech instruction as the recommended speech instruction is no greater than a predetermined threshold.
This invention relates to a method for managing speech instructions in a software system, particularly for updating and recommending speech instructions based on software updates. The problem addressed is ensuring that users are provided with the most current and relevant speech instructions while minimizing unnecessary prompts. The method involves determining the latest applicable speech instruction based on a version number of the software update. Before selecting this instruction as the recommended one, the system checks whether the number of times a prompt to select the latest instruction has been provided does not exceed a predetermined threshold. If the threshold is not exceeded, the prompt is displayed to the user. This ensures that users are notified of updates without being overwhelmed by repeated prompts. The method also includes steps for identifying applicable speech instructions, such as filtering instructions based on compatibility with the current software version and user preferences. The system may also track user interactions with previous prompts to refine future recommendations. The overall goal is to streamline the process of updating speech instructions while maintaining user engagement and reducing disruption.
6. The method of claim 2 , wherein the method further comprises: matching a user speech with the applicable speech instructions after the user speech is acquired; and when the user speech does not match with the applicable speech instructions, providing the prompt based on the recommended speech instruction.
7. A computer device, comprising a memory, a processor and a computer program stored on the memory and executable by the processor, wherein when the processor executes the computer program, the processor is caused to perform operations comprising: during a process of displaying an interface of an application, detecting a first user operation, wherein the first user operation is an operation for triggering a speech input widget; in response to the first user operation, querying a speech instruction associated with the application based on the application containing the interface, and querying a system general speech instruction; setting the speech instruction associated with the application and the system general speech instruction as applicable speech instructions for the application; providing a prompt based on the applicable speech instructions; wherein providing the prompt based on the applicable speech instructions comprises: querying a non-speech operation detected before detecting the first user operation; determining a target speech instruction from the applicable speech instructions based on the non-speech operation, wherein the non-speech operation can be replaced with the target speech instruction; and displaying the applicable speech instructions and highlighting the target speech instruction to prompt the user to use the target speech instruction to replace the non-speech operation.
This invention relates to a computer device that enhances user interaction with applications through speech input. The problem addressed is the inefficiency of traditional input methods, where users must manually perform repetitive or complex operations. The solution involves a system that detects a user's intent to use speech input, then dynamically suggests relevant voice commands based on the current application context and prior non-speech actions. The computer device includes a processor, memory, and a program that, when executed, performs several key functions. When a user triggers a speech input widget in an application interface, the system queries both application-specific speech instructions and general system-wide speech instructions. These are then set as applicable commands for the current application. The system analyzes non-speech operations performed before the speech input was triggered, identifies a target speech instruction that could replace those actions, and displays all applicable speech instructions while highlighting the most relevant one. This guides the user toward efficient voice-based alternatives for their recent manual inputs. The approach improves usability by reducing manual effort and providing context-aware voice command suggestions, making interactions with applications more intuitive and efficient.
8. The computer device of claim 7 , wherein, after setting the speech instruction associated with the application and the system general speech instruction as the applicable speech instructions for the application, the processor is caused to further perform operations comprising: when detecting a second user operation for inputting a speech, in response to the second user operation, selecting a recommended speech instruction from the applicable speech instructions; and providing the prompt based on the recommended speech instruction.
This invention relates to speech-based user interfaces in computer devices, specifically improving the selection and presentation of speech instructions for applications. The problem addressed is the inefficiency and ambiguity in current systems when users interact with applications via voice commands, leading to misinterpretation or unnecessary delays. The system includes a computer device with a processor that manages speech instructions for applications. The processor sets applicable speech instructions for an application by combining application-specific speech instructions with system-wide general speech instructions. When a user initiates a speech input, the processor selects a recommended speech instruction from the applicable set and provides a prompt based on this recommendation. This ensures that the most relevant and contextually appropriate speech instruction is prioritized, reducing user confusion and improving interaction efficiency. The processor dynamically adjusts the selection of recommended speech instructions based on user behavior and context, ensuring that the prompts are tailored to the user's needs. This approach enhances the usability of voice-controlled applications by minimizing ambiguity and streamlining the interaction process. The system is particularly useful in environments where quick and accurate voice-based interactions are critical, such as smart assistants, automotive interfaces, or accessibility tools.
9. The computer device of claim 8 , wherein, selecting the recommended speech instruction from the applicable speech instructions comprises: querying a usage counter of each applicable speech instruction; and selecting the recommended speech instruction from the applicable speech instructions based on the usage counter.
This invention relates to a computer device that improves speech interaction by recommending speech instructions based on usage frequency. The device includes a speech processing module that receives and processes speech input from a user. It also includes a speech instruction database storing multiple speech instructions, each associated with a usage counter tracking how often the instruction has been used. When a user provides a speech input, the device identifies applicable speech instructions from the database that match the input. To recommend the most relevant instruction, the device queries the usage counter for each applicable instruction and selects the one with the highest usage count. This ensures frequently used instructions are prioritized, enhancing user experience by reducing ambiguity and improving response accuracy. The system may also include a display for presenting the recommended instruction to the user. The invention addresses the problem of inefficient speech interaction by dynamically adapting recommendations based on historical usage data, making interactions more intuitive and efficient.
10. The computer device of claim 8 , wherein, selecting the recommended speech instruction from the applicable speech instructions comprises: querying a software update version for each newly added applicable speech instruction; and selecting a latest applicable speech instruction from the applicable speech instructions as the recommended speech instruction based on the software update version.
This invention relates to a computer device configured to select and recommend speech instructions for user interaction, particularly in systems where multiple applicable speech instructions may exist. The problem addressed is ensuring users receive the most relevant and up-to-date speech instructions, especially when multiple versions or updates of the same instruction are available. The computer device includes a processor and memory storing instructions that, when executed, perform operations to identify applicable speech instructions for a given context or user input. When multiple applicable instructions are found, the device selects the most appropriate one by querying the software update version associated with each newly added applicable speech instruction. The device then compares these versions and selects the latest applicable speech instruction as the recommended one. This ensures users receive the most current and relevant instructions, improving interaction efficiency and accuracy. The system may also prioritize instructions based on factors such as user preferences, historical usage, or system requirements, but the core selection mechanism relies on version comparison to determine the most recent update. This approach is particularly useful in dynamic environments where speech instructions are frequently updated or modified.
11. The computer device of claim 10 , wherein, before selecting the latest applicable speech instruction from the applicable speech instructions as the recommended speech instruction based on the software update version, the processor is caused to further perform operations comprising: determining the latest applicable speech instruction based on a version number of the software update version; and providing the prompt when a number of occurrences of providing the prompt to select the latest applicable speech instruction as the recommended speech instruction is no greater than a predetermined threshold.
A computer device is configured to manage speech instructions for software updates. The device includes a processor that executes operations to determine the latest applicable speech instruction based on a version number of a software update. The processor provides a prompt to a user to select this latest speech instruction as the recommended instruction, but only if the number of times the prompt has been provided does not exceed a predetermined threshold. This ensures that users are notified of updates without excessive repetition. The device also includes a memory storing the speech instructions and a communication interface for receiving the software update version. The processor further selects the latest applicable speech instruction from multiple applicable instructions based on the update version and updates the recommended speech instruction accordingly. This system helps maintain consistency in user interactions by aligning speech instructions with the latest software versions while controlling the frequency of user prompts.
12. The computer device of claim 8 , wherein the processor is caused to further perform operations comprising: matching a user speech with the applicable speech instructions after the user speech is acquired; and when the user speech does not match with the applicable speech instructions, providing the prompt based on the recommended speech instruction.
This invention relates to a computer device with speech recognition and guidance capabilities, particularly for assisting users in providing correct voice commands. The problem addressed is the mismatch between user speech and expected or required speech instructions, which can lead to errors or failed interactions in voice-controlled systems. The computer device includes a processor that performs operations to acquire user speech and compare it against applicable speech instructions stored in memory. If the user's speech does not match the expected instructions, the device provides a prompt based on a recommended speech instruction to guide the user toward a correct input. The system may also include a microphone for capturing speech and a display for presenting prompts or feedback. The recommended speech instruction is derived from a set of predefined instructions, ensuring consistency in user guidance. The invention improves user interaction by dynamically correcting speech input errors, reducing frustration and increasing the accuracy of voice-controlled operations. This is particularly useful in applications where precise voice commands are required, such as smart home systems, virtual assistants, or automated customer service platforms. The system ensures that users receive real-time feedback when their speech does not align with the expected format, enhancing usability and efficiency.
13. A non-temporary computer-readable storage medium, having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor is caused to perform operations comprising: during a process of displaying an interface of an application, detecting a first user operation, wherein the first user operation is an operation for triggering a speech input widget; in response to the first user operation, querying a speech instruction associated with the application based on the application containing the interface, and querying a system general speech instruction; setting the speech instruction associated with the application and the system general speech instruction as applicable speech instructions for the application; providing a prompt based on the applicable speech instructions; wherein providing the prompt based on the applicable speech instructions comprises: querying a non-speech operation detected before detecting the first user operation; determining a target speech instruction from the applicable speech instructions based on the non-speech operation, wherein the non-speech operation can be replaced with the target speech instruction; and displaying the applicable speech instructions and highlighting the target speech instruction to prompt the user to use the target speech instruction to replace the non-speech operation.
This invention relates to voice interaction systems in software applications, specifically improving user experience by dynamically suggesting speech commands based on prior non-speech actions. The problem addressed is the inefficiency of users manually performing repetitive tasks through traditional input methods when voice commands could streamline the process. The system operates by detecting a user's activation of a speech input widget within an application interface. In response, it retrieves two sets of voice commands: those specific to the current application and general system-wide commands. These are combined into a set of applicable voice instructions for the context. The system then analyzes recent non-speech operations (e.g., mouse clicks or keyboard inputs) performed before the speech widget activation. Based on this analysis, it identifies a target voice command that could replace the non-speech operation, then displays all applicable voice commands while visually emphasizing the target command. This guidance helps users transition from manual to voice-based interactions more efficiently by suggesting contextually relevant commands that match their recent actions. The approach aims to reduce learning curves and improve workflow efficiency by making voice interaction more intuitive and integrated with existing user behavior.
14. The non-temporary computer-readable storage medium of claim 13 , wherein, after setting the speech instruction associated with the application and the system general speech instruction as the applicable speech instructions for the application, the processor is caused to further perform operations comprising: when detecting a second user operation for inputting a speech, in response to the second user operation, selecting a recommended speech instruction from the applicable speech instructions; and providing the prompt based on the recommended speech instruction.
This invention relates to speech instruction management in computing systems, specifically improving user interaction with applications through optimized speech input. The problem addressed is the inefficiency of existing systems in dynamically selecting and applying speech instructions tailored to specific applications, leading to suboptimal user experiences. The system involves a non-temporary computer-readable storage medium storing instructions that, when executed by a processor, enable dynamic speech instruction selection. The processor sets speech instructions for an application, including both application-specific and system-wide general speech instructions, as applicable instructions. Upon detecting a user operation to input speech, the system selects a recommended speech instruction from the applicable instructions and provides a prompt based on this selection. This ensures that the speech input is contextually relevant to the current application, enhancing usability and reducing errors. The solution improves over prior art by dynamically adjusting speech instructions based on the application context, ensuring that the most relevant speech commands are prioritized. This reduces the need for manual selection and improves efficiency in voice-based interactions. The system is particularly useful in environments where multiple applications require distinct speech commands, such as smart assistants, voice-controlled interfaces, or accessibility tools. The invention streamlines speech input processes, making them more intuitive and responsive to user needs.
15. The non-temporary computer-readable storage medium of claim 14 , wherein, selecting the recommended speech instruction from the applicable speech instructions comprises: querying a usage counter of each applicable speech instruction; and selecting the recommended speech instruction from the applicable speech instructions based on the usage counter.
This invention relates to a system for selecting speech instructions in a voice-controlled environment, such as virtual assistants or automated customer service systems. The problem addressed is the inefficiency in selecting the most appropriate speech instruction from multiple applicable options, which can lead to user frustration or incorrect responses. The system improves upon prior art by incorporating a usage counter for each speech instruction. When multiple speech instructions are applicable to a given user input, the system queries the usage counter for each applicable instruction. The instruction with the highest usage count is then selected as the recommended speech instruction. This approach ensures that frequently used and likely more effective instructions are prioritized, improving system accuracy and user satisfaction. The usage counter tracks how often each speech instruction has been successfully executed in response to similar user inputs. By analyzing historical usage data, the system dynamically adjusts its recommendations, adapting to user preferences and common usage patterns. This method enhances the efficiency of voice-controlled systems by reducing the likelihood of selecting less optimal or outdated instructions. The system may also include additional features, such as updating the usage counter based on user feedback or system performance metrics, further refining the selection process over time.
16. The non-temporary computer-readable storage medium of claim 14 , wherein, selecting the recommended speech instruction from the applicable speech instructions comprises: querying a software update version for each newly added applicable speech instruction; and selecting a latest applicable speech instruction from the applicable speech instructions as the recommended speech instruction based on the software update version.
This invention relates to a system for managing and selecting speech instructions in a software application, particularly for updating and recommending the most current speech instructions to users. The system addresses the problem of ensuring users have access to the latest and most relevant speech instructions, which may change over time due to software updates or improvements. The invention involves a non-transitory computer-readable storage medium containing instructions that, when executed, perform a method for selecting a recommended speech instruction from a set of applicable speech instructions. The selection process includes querying the software update version for each newly added applicable speech instruction and then selecting the latest applicable speech instruction based on the software update version. This ensures that users are provided with the most up-to-date speech instructions, improving the accuracy and relevance of the instructions provided. The system may also involve storing and retrieving speech instructions from a database, categorizing them based on applicability, and dynamically updating the instructions as new versions of the software are released. The invention aims to enhance user experience by ensuring that the speech instructions are always current and aligned with the latest software updates.
17. The non-temporary computer-readable storage medium of claim 16 , wherein, before selecting the latest applicable speech instruction from the applicable speech instructions as the recommended speech instruction based on the software update version, the processor is caused to further perform operations comprising: determining the latest applicable speech instruction based on a version number of the software update version; and providing the prompt when a number of occurrences of providing the prompt to select the latest applicable speech instruction as the recommended speech instruction is no greater than a predetermined threshold.
This invention relates to a system for managing speech instructions in a software update process. The problem addressed is ensuring users are properly guided to adopt the most current speech instructions during software updates, while avoiding excessive or redundant prompts. The system involves a non-temporary computer-readable storage medium containing instructions that, when executed by a processor, cause the processor to perform operations. These operations include determining the latest applicable speech instruction based on the version number of the software update. The system then provides a prompt to the user to select this latest instruction as the recommended speech instruction, but only if the number of times the prompt has been provided does not exceed a predetermined threshold. This prevents over-prompting while ensuring users are aware of the most current instructions. The system also includes functionality to select the latest applicable speech instruction from a set of applicable instructions based on the software update version. This ensures compatibility and relevance of the instructions provided to the user. The prompt is designed to guide the user toward adopting the most up-to-date instructions without overwhelming them with repeated notifications. The threshold mechanism balances user experience with the need to ensure proper instruction adoption.
18. The non-temporary computer-readable storage medium of claim 14 , wherein the processor is caused to further perform operations comprising: matching a user speech with the applicable speech instructions after the user speech is acquired; and when the user speech does not match with the applicable speech instructions, providing the prompt based on the recommended speech instruction.
This invention relates to speech recognition and user interaction systems, specifically addressing the challenge of improving accuracy and user experience in voice-controlled applications. The system involves a computer-readable storage medium containing instructions that, when executed by a processor, enable a device to process user speech inputs and provide feedback when those inputs do not align with expected or recommended speech patterns. The system includes a speech recognition module that captures and analyzes user speech, comparing it against predefined speech instructions stored in a database. If the user's speech does not match the expected instructions, the system generates a prompt to guide the user toward the correct or recommended speech format. This prompt may include examples of acceptable speech inputs or instructions to clarify the expected response. The system may also log instances of mismatched speech for further analysis or training of the speech recognition model. The invention aims to enhance user interaction by reducing errors in voice commands, particularly in applications where precise speech input is critical, such as virtual assistants, automated customer service, or voice-controlled interfaces. By dynamically providing feedback when speech inputs are incorrect, the system improves usability and efficiency in voice-based interactions. The system may also adapt over time by updating the speech instruction database based on user feedback or performance data.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
May 21, 2019
February 1, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.